Online Learning with Feedback Graphs Without the Graphs
release_uivua4t5rrhxdbulm3etzm5uha
by
Alon Cohen, Tamir Hazan, Tomer Koren
2016
Abstract
We study an online learning framework introduced by Mannor and Shamir (2011)
in which the feedback is specified by a graph, in a setting where the graph may
vary from round to round and is never fully revealed to the learner. We
show a large gap between the adversarial and the stochastic cases. In the
adversarial case, we prove that even for dense feedback graphs, the learner
cannot improve upon a trivial regret bound obtained by ignoring any additional
feedback besides her own loss. In contrast, in the stochastic case we give an
algorithm that achieves Θ(√(α T)) regret over T
rounds, provided that the independence numbers of the hidden feedback graphs
are at most α. We also extend our results to a more general feedback
model, in which the learner does not necessarily observe her own loss, and show
that, even in simple cases, concealing the feedback graphs might render a
learnable problem unlearnable.
In text/plain
format
Archived Files and Locations
application/pdf 244.6 kB
file_vcem6itjfzespor52crpgbmpke
|
arxiv.org (repository) web.archive.org (webarchive) |
1605.07018v1
access all versions, variants, and formats of this works (eg, pre-prints)